In the end of October 2025 MiniMax has released the new Speech 2.6. This audio model delivers:
- Enhanced realism, new “Fluent” emotion
- More natural multilingual accents
- Smarter number reading
This update also extends language support to 40. You can fix up voice clones in other languages too with one click.
The voice sounds more natural now even when the original clip has an accent or isn’t super clear. It still keeps the voice’s tone but smooths out the speech.
If you'd like to access this model, you can explore the following possibilities:
